论文与解读

按年份浏览论文。每篇论文页面包含摘要、简要解读、Related Work 定位、参考来源和引用下载。

English catalog

原创解读采用 CC BY 4.0;论文摘要和书目信息仍保留原有权利。

2026 9

2025 3

2024 5

IcoCap: Improving Video Captioning by Compounding Images

Yuanzhi Liang, Linchao Zhu, et al. · IEEE Transactions on Multimedia · 2024 · 卷 26 · 页 4389-4400

IcoCap 改变视频 captioner 看到的内容密度:Image-Video Compounding Strategy(ICS)把简洁图像语义复合进视频样本,Visual-Semantic Guided Captioning(VGC)再让 caption supervision 适应复合内容中的歧义。

2023 1

2022 2

2021 2

Food and Ingredient Joint Learning for Fine-Grained Recognition

Chengxu Liu, Yuanzhi Liang, et al. · IEEE Transactions on Circuits and Systems for Video Technology · 2021 · 卷 31(6) · 页 2480-2493

论文以 Attention Fusion Network 强调判别区域,并通过 Food-Ingredient Joint Learning module 与 balance focal loss 联合学习菜品类别和食材,以缓解 ingredient imbalance。

Removing Raindrops and Rain Streaks in One Go

Ruijie Quan, Xin Yu, et al. · IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021) · 2021 · 页 9143-9152

该方法包含 raindrop→streak 和 streak→raindrop 两条互补级联分支,以 attention 融合输出,用 neural architecture search 搜索去雨模块,并提出真实世界 RainDS 数据集。

2019 1